Merge tag 'xfs-5.6-merge-6' of git://git.kernel.org/pub/scm/fs/xfs/xfs-linux

Pull xfs updates from Darrick Wong:
 "In this release we clean out the last of the old 32-bit timestamp
  code, fix a number of bugs and memory corruptions on 32-bit platforms,
  and a refactoring of some of the extended attribute code.

  I think I'll be back next week with some refactoring of how the XFS
  buffer code returns error codes, however I prefer to hold onto that
  for another week to let it soak a while longer

  Summary:

   - Get rid of compat_time_t

   - Convert time_t to time64_t in quota code

   - Remove shadow variables

   - Prevent ATTR_ flag misuse in the attrmulti ioctls

   - Clean out strlen in the attr code

   - Remove some bogus asserts

   - Fix various file size limit calculation errors with 32-bit kernels

   - Pack xfs_dir2_sf_entry_t to fix build errors on arm oabi

   - Fix nowait inode locking calls for directio aio reads

   - Fix memory corruption bugs when invalidating remote xattr value
     buffers

   - Streamline remote attr value removal

   - Make the buffer log format size consistent across platforms

   - Strengthen buffer log format size checking

   - Fix messed up return types of xfs_inode_need_cow

   - Fix some unused variable warnings"

* tag 'xfs-5.6-merge-6' of git://git.kernel.org/pub/scm/fs/xfs/xfs-linux: (24 commits)
  xfs: remove unused variable 'done'
  xfs: fix uninitialized variable in xfs_attr3_leaf_inactive
  xfs: change return value of xfs_inode_need_cow to int
  xfs: check log iovec size to make sure it's plausibly a buffer log format
  xfs: make struct xfs_buf_log_format have a consistent size
  xfs: complain if anyone tries to create a too-large buffer log item
  xfs: clean up xfs_buf_item_get_format return value
  xfs: streamline xfs_attr3_leaf_inactive
  xfs: fix memory corruption during remote attr value buffer invalidation
  xfs: refactor remote attr value buffer invalidation
  xfs: fix IOCB_NOWAIT handling in xfs_file_dio_aio_read
  xfs: Add __packed to xfs_dir2_sf_entry_t definition
  xfs: fix s_maxbytes computation on 32-bit kernels
  xfs: truncate should remove all blocks, not just to the end of the page cache
  xfs: introduce XFS_MAX_FILEOFF
  xfs: remove bogus assertion when online repair isn't enabled
  xfs: Remove all strlen in all xfs_attr_* functions for attr names.
  xfs: fix misuse of the XFS_ATTR_INCOMPLETE flag
  xfs: also remove cached ACLs when removing the underlying attr
  xfs: reject invalid flags combinations in XFS_IOC_ATTRMULTI_BY_HANDLE
  ...

fs/xfs/libxfs/xfs_attr.c

@@ -62,6 +62,7 @@ xfs_attr_args_init(
 	struct xfs_da_args	*args,
 	struct xfs_inode	*dp,
 	const unsigned char	*name,
+	size_t			namelen,
 	int			flags)
 {
 
@@ -74,7 +75,7 @@ xfs_attr_args_init(
 	args->dp = dp;
 	args->flags = flags;
 	args->name = name;
-	args->namelen = strlen((const char *)name);
+	args->namelen = namelen;
 	if (args->namelen >= MAXNAMELEN)
 		return -EFAULT;		/* match IRIX behaviour */
 
@@ -139,6 +140,7 @@ int
 xfs_attr_get(
 	struct xfs_inode	*ip,
 	const unsigned char	*name,
+	size_t			namelen,
 	unsigned char		**value,
 	int			*valuelenp,
 	int			flags)
@@ -154,7 +156,7 @@ xfs_attr_get(
 	if (XFS_FORCED_SHUTDOWN(ip->i_mount))
 		return -EIO;
 
-	error = xfs_attr_args_init(&args, ip, name, flags);
+	error = xfs_attr_args_init(&args, ip, name, namelen, flags);
 	if (error)
 		return error;
 
@@ -338,6 +340,7 @@ int
 xfs_attr_set(
 	struct xfs_inode	*dp,
 	const unsigned char	*name,
+	size_t			namelen,
 	unsigned char		*value,
 	int			valuelen,
 	int			flags)
@@ -353,7 +356,7 @@ xfs_attr_set(
 	if (XFS_FORCED_SHUTDOWN(dp->i_mount))
 		return -EIO;
 
-	error = xfs_attr_args_init(&args, dp, name, flags);
+	error = xfs_attr_args_init(&args, dp, name, namelen, flags);
 	if (error)
 		return error;
 
@@ -442,6 +445,7 @@ int
 xfs_attr_remove(
 	struct xfs_inode	*dp,
 	const unsigned char	*name,
+	size_t			namelen,
 	int			flags)
 {
 	struct xfs_mount	*mp = dp->i_mount;
@@ -453,7 +457,7 @@ xfs_attr_remove(
 	if (XFS_FORCED_SHUTDOWN(dp->i_mount))
 		return -EIO;
 
-	error = xfs_attr_args_init(&args, dp, name, flags);
+	error = xfs_attr_args_init(&args, dp, name, namelen, flags);
 	if (error)
 		return error;
 
@@ -1007,7 +1011,7 @@ xfs_attr_node_addname(
 		 * The INCOMPLETE flag means that we will find the "old"
 		 * attr, not the "new" one.
 		 */
-		args->flags |= XFS_ATTR_INCOMPLETE;
+		args->op_flags |= XFS_DA_OP_INCOMPLETE;
 		state = xfs_da_state_alloc();
 		state->args = args;
 		state->mp = mp;

fs/xfs/libxfs/xfs_attr.h

@@ -26,7 +26,7 @@ struct xfs_attr_list_context;
  *========================================================================*/
 
 
-#define ATTR_DONTFOLLOW	0x0001	/* -- unused, from IRIX -- */
+#define ATTR_DONTFOLLOW	0x0001	/* -- ignored, from IRIX -- */
 #define ATTR_ROOT	0x0002	/* use attrs in root (trusted) namespace */
 #define ATTR_TRUST	0x0004	/* -- unused, from IRIX -- */
 #define ATTR_SECURE	0x0008	/* use attrs in security namespace */
@@ -37,7 +37,10 @@ struct xfs_attr_list_context;
 #define ATTR_KERNOVAL	0x2000	/* [kernel] get attr size only, not value */
 
 #define ATTR_INCOMPLETE	0x4000	/* [kernel] return INCOMPLETE attr keys */
-#define ATTR_ALLOC	0x8000	/* allocate xattr buffer on demand */
+#define ATTR_ALLOC	0x8000	/* [kernel] allocate xattr buffer on demand */
+
+#define ATTR_KERNEL_FLAGS \
+	(ATTR_KERNOTIME | ATTR_KERNOVAL | ATTR_INCOMPLETE | ATTR_ALLOC)
 
 #define XFS_ATTR_FLAGS \
 	{ ATTR_DONTFOLLOW, 	"DONTFOLLOW" }, \
@@ -145,11 +148,13 @@ int xfs_attr_list_int(struct xfs_attr_list_context *);
 int xfs_inode_hasattr(struct xfs_inode *ip);
 int xfs_attr_get_ilocked(struct xfs_inode *ip, struct xfs_da_args *args);
 int xfs_attr_get(struct xfs_inode *ip, const unsigned char *name,
-		 unsigned char **value, int *valuelenp, int flags);
+		 size_t namelen, unsigned char **value, int *valuelenp,
+		 int flags);
 int xfs_attr_set(struct xfs_inode *dp, const unsigned char *name,
-		 unsigned char *value, int valuelen, int flags);
+		 size_t namelen, unsigned char *value, int valuelen, int flags);
 int xfs_attr_set_args(struct xfs_da_args *args);
-int xfs_attr_remove(struct xfs_inode *dp, const unsigned char *name, int flags);
+int xfs_attr_remove(struct xfs_inode *dp, const unsigned char *name,
+		    size_t namelen, int flags);
 int xfs_attr_remove_args(struct xfs_da_args *args);
 int xfs_attr_list(struct xfs_inode *dp, char *buffer, int bufsize,
 		  int flags, struct attrlist_cursor_kern *cursor);

fs/xfs/libxfs/xfs_attr_leaf.c

@@ -2403,8 +2403,8 @@ xfs_attr3_leaf_lookup_int(
 		 * If we are looking for INCOMPLETE entries, show only those.
 		 * If we are looking for complete entries, show only those.
 		 */
-		if ((args->flags & XFS_ATTR_INCOMPLETE) !=
-		    (entry->flags & XFS_ATTR_INCOMPLETE)) {
+		if (!!(args->op_flags & XFS_DA_OP_INCOMPLETE) !=
+		    !!(entry->flags & XFS_ATTR_INCOMPLETE)) {
 			continue;
 		}
 		if (entry->flags & XFS_ATTR_LOCAL) {

fs/xfs/libxfs/xfs_attr_leaf.h

@@ -39,15 +39,6 @@ struct xfs_attr3_icleaf_hdr {
 	} freemap[XFS_ATTR_LEAF_MAPSIZE];
 };
 
-/*
- * Used to keep a list of "remote value" extents when unlinking an inode.
- */
-typedef struct xfs_attr_inactive_list {
-	xfs_dablk_t	valueblk;	/* block number of value bytes */
-	int		valuelen;	/* number of bytes in value */
-} xfs_attr_inactive_list_t;
-
-
 /*========================================================================
  * Function prototypes for the kernel.
  *========================================================================*/

fs/xfs/libxfs/xfs_attr_remote.c

@@ -25,6 +25,23 @@
 
 #define ATTR_RMTVALUE_MAPSIZE	1	/* # of map entries at once */
 
+/*
+ * Remote Attribute Values
+ * =======================
+ *
+ * Remote extended attribute values are conceptually simple -- they're written
+ * to data blocks mapped by an inode's attribute fork, and they have an upper
+ * size limit of 64k.  Setting a value does not involve the XFS log.
+ *
+ * However, on a v5 filesystem, maximally sized remote attr values require one
+ * block more than 64k worth of space to hold both the remote attribute value
+ * header (64 bytes).  On a 4k block filesystem this results in a 68k buffer;
+ * on a 64k block filesystem, this would be a 128k buffer.  Note that the log
+ * format can only handle a dirty buffer of XFS_MAX_BLOCKSIZE length (64k).
+ * Therefore, we /must/ ensure that remote attribute value buffers never touch
+ * the logging system and therefore never have a log item.
+ */
+
 /*
  * Each contiguous block has a header, so it is not just a simple attribute
  * length to FSB conversion.
@@ -401,17 +418,25 @@ xfs_attr_rmtval_get(
 			       (map[i].br_startblock != HOLESTARTBLOCK));
 			dblkno = XFS_FSB_TO_DADDR(mp, map[i].br_startblock);
 			dblkcnt = XFS_FSB_TO_BB(mp, map[i].br_blockcount);
-			error = xfs_trans_read_buf(mp, args->trans,
-						   mp->m_ddev_targp,
-						   dblkno, dblkcnt, 0, &bp,
-						   &xfs_attr3_rmt_buf_ops);
-			if (error)
+			bp = xfs_buf_read(mp->m_ddev_targp, dblkno, dblkcnt, 0,
+					&xfs_attr3_rmt_buf_ops);
+			if (!bp)
+				return -ENOMEM;
+			error = bp->b_error;
+			if (error) {
+				xfs_buf_ioerror_alert(bp, __func__);
+				xfs_buf_relse(bp);
+
+				/* bad CRC means corrupted metadata */
+				if (error == -EFSBADCRC)
+					error = -EFSCORRUPTED;
 				return error;
+			}
 
 			error = xfs_attr_rmtval_copyout(mp, bp, args->dp->i_ino,
 							&offset, &valuelen,
 							&dst);
-			xfs_trans_brelse(args->trans, bp);
+			xfs_buf_relse(bp);
 			if (error)
 				return error;
 
@@ -552,6 +577,33 @@ xfs_attr_rmtval_set(
 	return 0;
 }
 
+/* Mark stale any incore buffers for the remote value. */
+int
+xfs_attr_rmtval_stale(
+	struct xfs_inode	*ip,
+	struct xfs_bmbt_irec	*map,
+	xfs_buf_flags_t		incore_flags)
+{
+	struct xfs_mount	*mp = ip->i_mount;
+	struct xfs_buf		*bp;
+
+	ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL));
+
+	if (XFS_IS_CORRUPT(mp, map->br_startblock == DELAYSTARTBLOCK) ||
+	    XFS_IS_CORRUPT(mp, map->br_startblock == HOLESTARTBLOCK))
+		return -EFSCORRUPTED;
+
+	bp = xfs_buf_incore(mp->m_ddev_targp,
+			XFS_FSB_TO_DADDR(mp, map->br_startblock),
+			XFS_FSB_TO_BB(mp, map->br_blockcount), incore_flags);
+	if (bp) {
+		xfs_buf_stale(bp);
+		xfs_buf_relse(bp);
+	}
+
+	return 0;
+}
+
 /*
  * Remove the value associated with an attribute by deleting the
  * out-of-line buffer that it is stored on.
@@ -560,7 +612,6 @@ int
 xfs_attr_rmtval_remove(
 	struct xfs_da_args	*args)
 {
-	struct xfs_mount	*mp = args->dp->i_mount;
 	xfs_dablk_t		lblkno;
 	int			blkcnt;
 	int			error;
@@ -575,9 +626,6 @@ xfs_attr_rmtval_remove(
 	blkcnt = args->rmtblkcnt;
 	while (blkcnt > 0) {
 		struct xfs_bmbt_irec	map;
-		struct xfs_buf		*bp;
-		xfs_daddr_t		dblkno;
-		int			dblkcnt;
 		int			nmap;
 
 		/*
@@ -588,22 +636,11 @@ xfs_attr_rmtval_remove(
 				       blkcnt, &map, &nmap, XFS_BMAPI_ATTRFORK);
 		if (error)
 			return error;
-		ASSERT(nmap == 1);
-		ASSERT((map.br_startblock != DELAYSTARTBLOCK) &&
-		       (map.br_startblock != HOLESTARTBLOCK));
-
-		dblkno = XFS_FSB_TO_DADDR(mp, map.br_startblock),
-		dblkcnt = XFS_FSB_TO_BB(mp, map.br_blockcount);
-
-		/*
-		 * If the "remote" value is in the cache, remove it.
-		 */
-		bp = xfs_buf_incore(mp->m_ddev_targp, dblkno, dblkcnt, XBF_TRYLOCK);
-		if (bp) {
-			xfs_buf_stale(bp);
-			xfs_buf_relse(bp);
-			bp = NULL;
-		}
+		if (XFS_IS_CORRUPT(args->dp->i_mount, nmap != 1))
+			return -EFSCORRUPTED;
+		error = xfs_attr_rmtval_stale(args->dp, &map, XBF_TRYLOCK);
+		if (error)
+			return error;
 
 		lblkno += map.br_blockcount;
 		blkcnt -= map.br_blockcount;

fs/xfs/libxfs/xfs_attr_remote.h

@@ -11,5 +11,7 @@ int xfs_attr3_rmt_blocks(struct xfs_mount *mp, int attrlen);
 int xfs_attr_rmtval_get(struct xfs_da_args *args);
 int xfs_attr_rmtval_set(struct xfs_da_args *args);
 int xfs_attr_rmtval_remove(struct xfs_da_args *args);
+int xfs_attr_rmtval_stale(struct xfs_inode *ip, struct xfs_bmbt_irec *map,
+		xfs_buf_flags_t incore_flags);
 
 #endif /* __XFS_ATTR_REMOTE_H__ */

fs/xfs/libxfs/xfs_btree.c

@@ -2389,8 +2389,6 @@ xfs_btree_lshift(
 	XFS_BTREE_STATS_ADD(cur, moves, rrecs - 1);
 	if (level > 0) {
 		/* It's a nonleaf. operate on keys and ptrs */
-		int			i;		/* loop index */
-
 		for (i = 0; i < rrecs; i++) {
 			error = xfs_btree_debug_check_ptr(cur, rpp, i + 1, level);
 			if (error)

fs/xfs/libxfs/xfs_da_btree.h

@@ -89,6 +89,7 @@ typedef struct xfs_da_args {
 #define XFS_DA_OP_OKNOENT	0x0008	/* lookup/add op, ENOENT ok, else die */
 #define XFS_DA_OP_CILOOKUP	0x0010	/* lookup to return CI name if found */
 #define XFS_DA_OP_ALLOCVAL	0x0020	/* lookup to alloc buffer if found  */
+#define XFS_DA_OP_INCOMPLETE	0x0040	/* lookup INCOMPLETE attr keys */
 
 #define XFS_DA_OP_FLAGS \
 	{ XFS_DA_OP_JUSTCHECK,	"JUSTCHECK" }, \
@@ -96,7 +97,8 @@ typedef struct xfs_da_args {
 	{ XFS_DA_OP_ADDNAME,	"ADDNAME" }, \
 	{ XFS_DA_OP_OKNOENT,	"OKNOENT" }, \
 	{ XFS_DA_OP_CILOOKUP,	"CILOOKUP" }, \
-	{ XFS_DA_OP_ALLOCVAL,	"ALLOCVAL" }
+	{ XFS_DA_OP_ALLOCVAL,	"ALLOCVAL" }, \
+	{ XFS_DA_OP_INCOMPLETE,	"INCOMPLETE" }
 
 /*
  * Storage for holding state during Btree searches and split/join ops.

fs/xfs/libxfs/xfs_da_format.h

@@ -217,7 +217,7 @@ typedef struct xfs_dir2_sf_entry {
 	 * A 64-bit or 32-bit inode number follows here, at a variable offset
 	 * after the name.
 	 */
-} xfs_dir2_sf_entry_t;
+} __packed xfs_dir2_sf_entry_t;
 
 static inline int xfs_dir2_sf_hdr_size(int i8count)
 {
@@ -683,8 +683,6 @@ struct xfs_attr3_leafblock {
 
 /*
  * Flags used in the leaf_entry[i].flags field.
- * NOTE: the INCOMPLETE bit must not collide with the flags bits specified
- * on the system call, they are "or"ed together for various operations.
  */
 #define	XFS_ATTR_LOCAL_BIT	0	/* attr is stored locally */
 #define	XFS_ATTR_ROOT_BIT	1	/* limit access to trusted attrs */

fs/xfs/libxfs/xfs_format.h

@@ -1540,6 +1540,13 @@ typedef struct xfs_bmdr_block {
 #define BMBT_BLOCKCOUNT_BITLEN	21
 
 #define BMBT_STARTOFF_MASK	((1ULL << BMBT_STARTOFF_BITLEN) - 1)
+#define BMBT_BLOCKCOUNT_MASK	((1ULL << BMBT_BLOCKCOUNT_BITLEN) - 1)
+
+/*
+ * bmbt records have a file offset (block) field that is 54 bits wide, so this
+ * is the largest xfs_fileoff_t that we ever expect to see.
+ */
+#define XFS_MAX_FILEOFF		(BMBT_STARTOFF_MASK + BMBT_BLOCKCOUNT_MASK)
 
 typedef struct xfs_bmbt_rec {
 	__be64			l0, l1;

fs/xfs/libxfs/xfs_log_format.h

@@ -462,11 +462,20 @@ static inline uint xfs_log_dinode_size(int version)
 #define	XFS_BLF_GDQUOT_BUF	(1<<4)
 
 /*
- * This is the structure used to lay out a buf log item in the
- * log.  The data map describes which 128 byte chunks of the buffer
- * have been logged.
- */
-#define XFS_BLF_DATAMAP_SIZE	((XFS_MAX_BLOCKSIZE / XFS_BLF_CHUNK) / NBWORD)
+ * This is the structure used to lay out a buf log item in the log.  The data
+ * map describes which 128 byte chunks of the buffer have been logged.
+ *
+ * The placement of blf_map_size causes blf_data_map to start at an odd
+ * multiple of sizeof(unsigned int) offset within the struct.  Because the data
+ * bitmap size will always be an even number, the end of the data_map (and
+ * therefore the structure) will also be at an odd multiple of sizeof(unsigned
+ * int).  Some 64-bit compilers will insert padding at the end of the struct to
+ * ensure 64-bit alignment of blf_blkno, but 32-bit ones will not.  Therefore,
+ * XFS_BLF_DATAMAP_SIZE must be an odd number to make the padding explicit and
+ * keep the structure size consistent between 32-bit and 64-bit platforms.
+ */
+#define __XFS_BLF_DATAMAP_SIZE	((XFS_MAX_BLOCKSIZE / XFS_BLF_CHUNK) / NBWORD)
+#define XFS_BLF_DATAMAP_SIZE	(__XFS_BLF_DATAMAP_SIZE + 1)
 
 typedef struct xfs_buf_log_format {
 	unsigned short	blf_type;	/* buf log item type indicator */

fs/xfs/scrub/repair.h

@@ -75,7 +75,6 @@ static inline xfs_extlen_t
 xrep_calc_ag_resblks(
 	struct xfs_scrub	*sc)
 {
-	ASSERT(!(sc->sm->sm_flags & XFS_SCRUB_IFLAG_REPAIR));
 	return 0;
 }
 

fs/xfs/xfs_acl.c

@@ -145,7 +145,8 @@ xfs_get_acl(struct inode *inode, int type)
 	 * go out to the disk.
 	 */
 	len = XFS_ACL_MAX_SIZE(ip->i_mount);
-	error = xfs_attr_get(ip, ea_name, (unsigned char **)&xfs_acl, &len,
+	error = xfs_attr_get(ip, ea_name, strlen(ea_name),
+				(unsigned char **)&xfs_acl, &len,
 				ATTR_ALLOC | ATTR_ROOT);
 	if (error) {
 		/*
@@ -196,15 +197,17 @@ __xfs_set_acl(struct inode *inode, struct posix_acl *acl, int type)
 		len -= sizeof(struct xfs_acl_entry) *
 			 (XFS_ACL_MAX_ENTRIES(ip->i_mount) - acl->a_count);
 
-		error = xfs_attr_set(ip, ea_name, (unsigned char *)xfs_acl,
-				len, ATTR_ROOT);
+		error = xfs_attr_set(ip, ea_name, strlen(ea_name),
+				     (unsigned char *)xfs_acl, len, ATTR_ROOT);
 
 		kmem_free(xfs_acl);
 	} else {
 		/*
 		 * A NULL ACL argument means we want to remove the ACL.
 		 */
-		error = xfs_attr_remove(ip, ea_name, ATTR_ROOT);
+		error = xfs_attr_remove(ip, ea_name,
+					strlen(ea_name),
+					ATTR_ROOT);
 
 		/*
 		 * If the attribute didn't exist to start with that's fine.

fs/xfs/xfs_attr_inactive.c

@@ -25,22 +25,18 @@
 #include "xfs_error.h"
 
 /*
- * Look at all the extents for this logical region,
- * invalidate any buffers that are incore/in transactions.
+ * Invalidate any incore buffers associated with this remote attribute value
+ * extent.   We never log remote attribute value buffers, which means that they
+ * won't be attached to a transaction and are therefore safe to mark stale.
+ * The actual bunmapi will be taken care of later.
  */
 STATIC int
-xfs_attr3_leaf_freextent(
-	struct xfs_trans	**trans,
+xfs_attr3_rmt_stale(
 	struct xfs_inode	*dp,
 	xfs_dablk_t		blkno,
 	int			blkcnt)
 {
 	struct xfs_bmbt_irec	map;
-	struct xfs_buf		*bp;
-	xfs_dablk_t		tblkno;
-	xfs_daddr_t		dblkno;
-	int			tblkcnt;
-	int			dblkcnt;
 	int			nmap;
 	int			error;
 
@@ -48,47 +44,29 @@ xfs_attr3_leaf_freextent(
 	 * Roll through the "value", invalidating the attribute value's
 	 * blocks.
 	 */
-	tblkno = blkno;
-	tblkcnt = blkcnt;
-	while (tblkcnt > 0) {
+	while (blkcnt > 0) {
 		/*
 		 * Try to remember where we decided to put the value.
 		 */
 		nmap = 1;
-		error = xfs_bmapi_read(dp, (xfs_fileoff_t)tblkno, tblkcnt,
+		error = xfs_bmapi_read(dp, (xfs_fileoff_t)blkno, blkcnt,
 				       &map, &nmap, XFS_BMAPI_ATTRFORK);
-		if (error) {
+		if (error)
 			return error;
-		}
-		ASSERT(nmap == 1);
-		ASSERT(map.br_startblock != DELAYSTARTBLOCK);
+		if (XFS_IS_CORRUPT(dp->i_mount, nmap != 1))
+			return -EFSCORRUPTED;
 
 		/*
-		 * If it's a hole, these are already unmapped
-		 * so there's nothing to invalidate.
+		 * Mark any incore buffers for the remote value as stale.  We
+		 * never log remote attr value buffers, so the buffer should be
+		 * easy to kill.
 		 */
-		if (map.br_startblock != HOLESTARTBLOCK) {
-
-			dblkno = XFS_FSB_TO_DADDR(dp->i_mount,
-						  map.br_startblock);
-			dblkcnt = XFS_FSB_TO_BB(dp->i_mount,
-						map.br_blockcount);
-			bp = xfs_trans_get_buf(*trans,
-					dp->i_mount->m_ddev_targp,
-					dblkno, dblkcnt, 0);
-			if (!bp)
-				return -ENOMEM;
-			xfs_trans_binval(*trans, bp);
-			/*
-			 * Roll to next transaction.
-			 */
-			error = xfs_trans_roll_inode(trans, dp);
-			if (error)
-				return error;
-		}
+		error = xfs_attr_rmtval_stale(dp, &map, 0);
+		if (error)
+			return error;
 
-		tblkno += map.br_blockcount;
-		tblkcnt -= map.br_blockcount;
+		blkno += map.br_blockcount;
+		blkcnt -= map.br_blockcount;
 	}
 
 	return 0;
@@ -102,86 +80,45 @@ xfs_attr3_leaf_freextent(
  */
 STATIC int
 xfs_attr3_leaf_inactive(
-	struct xfs_trans	**trans,
-	struct xfs_inode	*dp,
-	struct xfs_buf		*bp)
+	struct xfs_trans		**trans,
+	struct xfs_inode		*dp,
+	struct xfs_buf			*bp)
 {
-	struct xfs_attr_leafblock *leaf;
-	struct xfs_attr3_icleaf_hdr ichdr;
-	struct xfs_attr_leaf_entry *entry;
+	struct xfs_attr3_icleaf_hdr	ichdr;
+	struct xfs_mount		*mp = bp->b_mount;
+	struct xfs_attr_leafblock	*leaf = bp->b_addr;
+	struct xfs_attr_leaf_entry	*entry;
 	struct xfs_attr_leaf_name_remote *name_rmt;
-	struct xfs_attr_inactive_list *list;
-	struct xfs_attr_inactive_list *lp;
-	int			error;
-	int			count;
-	int			size;
-	int			tmp;
-	int			i;
-	struct xfs_mount	*mp = bp->b_mount;
+	int				error = 0;
+	int				i;
 
-	leaf = bp->b_addr;
 	xfs_attr3_leaf_hdr_from_disk(mp->m_attr_geo, &ichdr, leaf);
 
 	/*
-	 * Count the number of "remote" value extents.
+	 * Find the remote value extents for this leaf and invalidate their
+	 * incore buffers.
 	 */
-	count = 0;
 	entry = xfs_attr3_leaf_entryp(leaf);
 	for (i = 0; i < ichdr.count; entry++, i++) {
-		if (be16_to_cpu(entry->nameidx) &&
-		    ((entry->flags & XFS_ATTR_LOCAL) == 0)) {
-			name_rmt = xfs_attr3_leaf_name_remote(leaf, i);
-			if (name_rmt->valueblk)
-				count++;
-		}
-	}
+		int		blkcnt;
 
-	/*
-	 * If there are no "remote" values, we're done.
-	 */
-	if (count == 0) {
-		xfs_trans_brelse(*trans, bp);
-		return 0;
-	}
-
-	/*
-	 * Allocate storage for a list of all the "remote" value extents.
-	 */
-	size = count * sizeof(xfs_attr_inactive_list_t);
-	list = kmem_alloc(size, 0);
-
-	/*
-	 * Identify each of the "remote" value extents.
-	 */
-	lp = list;
-	entry = xfs_attr3_leaf_entryp(leaf);
-	for (i = 0; i < ichdr.count; entry++, i++) {
-		if (be16_to_cpu(entry->nameidx) &&
-		    ((entry->flags & XFS_ATTR_LOCAL) == 0)) {
-			name_rmt = xfs_attr3_leaf_name_remote(leaf, i);
-			if (name_rmt->valueblk) {
-				lp->valueblk = be32_to_cpu(name_rmt->valueblk);
-				lp->valuelen = xfs_attr3_rmt_blocks(dp->i_mount,
-						    be32_to_cpu(name_rmt->valuelen));
-				lp++;
-			}
-		}
-	}
-	xfs_trans_brelse(*trans, bp);	/* unlock for trans. in freextent() */
+		if (!entry->nameidx || (entry->flags & XFS_ATTR_LOCAL))
+			continue;
 
-	/*
-	 * Invalidate each of the "remote" value extents.
-	 */
-	error = 0;
-	for (lp = list, i = 0; i < count; i++, lp++) {
-		tmp = xfs_attr3_leaf_freextent(trans, dp,
-				lp->valueblk, lp->valuelen);
+		name_rmt = xfs_attr3_leaf_name_remote(leaf, i);
+		if (!name_rmt->valueblk)
+			continue;
 
-		if (error == 0)
-			error = tmp;	/* save only the 1st errno */
+		blkcnt = xfs_attr3_rmt_blocks(dp->i_mount,
+				be32_to_cpu(name_rmt->valuelen));
+		error = xfs_attr3_rmt_stale(dp,
+				be32_to_cpu(name_rmt->valueblk), blkcnt);
+		if (error)
+			goto err;
 	}
 
-	kmem_free(list);
+	xfs_trans_brelse(*trans, bp);
+err:
 	return error;
 }
 

fs/xfs/xfs_buf_item.c

@@ -27,6 +27,23 @@ static inline struct xfs_buf_log_item *BUF_ITEM(struct xfs_log_item *lip)
 
 STATIC void	xfs_buf_do_callbacks(struct xfs_buf *bp);
 
+/* Is this log iovec plausibly large enough to contain the buffer log format? */
+bool
+xfs_buf_log_check_iovec(
+	struct xfs_log_iovec		*iovec)
+{
+	struct xfs_buf_log_format	*blfp = iovec->i_addr;
+	char				*bmp_end;
+	char				*item_end;
+
+	if (offsetof(struct xfs_buf_log_format, blf_data_map) > iovec->i_len)
+		return false;
+
+	item_end = (char *)iovec->i_addr + iovec->i_len;
+	bmp_end = (char *)&blfp->blf_data_map[blfp->blf_map_size];
+	return bmp_end <= item_end;
+}
+
 static inline int
 xfs_buf_log_format_size(
 	struct xfs_buf_log_format *blfp)
@@ -688,7 +705,7 @@ static const struct xfs_item_ops xfs_buf_item_ops = {
 	.iop_push	= xfs_buf_item_push,
 };
 
-STATIC int
+STATIC void
 xfs_buf_item_get_format(
 	struct xfs_buf_log_item	*bip,
 	int			count)
@@ -698,14 +715,11 @@ xfs_buf_item_get_format(
 
 	if (count == 1) {
 		bip->bli_formats = &bip->__bli_format;
-		return 0;
+		return;
 	}
 
 	bip->bli_formats = kmem_zalloc(count * sizeof(struct xfs_buf_log_format),
 				0);
-	if (!bip->bli_formats)
-		return -ENOMEM;
-	return 0;
 }
 
 STATIC void
@@ -731,7 +745,6 @@ xfs_buf_item_init(
 	struct xfs_buf_log_item	*bip = bp->b_log_item;
 	int			chunks;
 	int			map_size;
-	int			error;
 	int			i;
 
 	/*
@@ -760,19 +773,22 @@ xfs_buf_item_init(
 	 * Discontiguous buffer support follows the layout of the underlying
 	 * buffer. This makes the implementation as simple as possible.
 	 */
-	error = xfs_buf_item_get_format(bip, bp->b_map_count);
-	ASSERT(error == 0);
-	if (error) {	/* to stop gcc throwing set-but-unused warnings */
-		kmem_cache_free(xfs_buf_item_zone, bip);
-		return error;
-	}
-
+	xfs_buf_item_get_format(bip, bp->b_map_count);
 
 	for (i = 0; i < bip->bli_format_count; i++) {
 		chunks = DIV_ROUND_UP(BBTOB(bp->b_maps[i].bm_len),
 				      XFS_BLF_CHUNK);
 		map_size = DIV_ROUND_UP(chunks, NBWORD);
 
+		if (map_size > XFS_BLF_DATAMAP_SIZE) {
+			kmem_cache_free(xfs_buf_item_zone, bip);
+			xfs_err(mp,
+	"buffer item dirty bitmap (%u uints) too small to reflect %u bytes!",
+					map_size,
+					BBTOB(bp->b_maps[i].bm_len));
+			return -EFSCORRUPTED;
+		}
+
 		bip->bli_formats[i].blf_type = XFS_LI_BUF;
 		bip->bli_formats[i].blf_blkno = bp->b_maps[i].bm_bn;
 		bip->bli_formats[i].blf_len = bp->b_maps[i].bm_len;
@@ -805,6 +821,9 @@ xfs_buf_item_log_segment(
 	uint		end_bit;
 	uint		mask;
 
+	ASSERT(first < XFS_BLF_DATAMAP_SIZE * XFS_BLF_CHUNK * NBWORD);
+	ASSERT(last < XFS_BLF_DATAMAP_SIZE * XFS_BLF_CHUNK * NBWORD);
+
 	/*
 	 * Convert byte offsets to bit numbers.
 	 */

fs/xfs/xfs_buf_item.h

@@ -61,6 +61,7 @@ void	xfs_buf_iodone_callbacks(struct xfs_buf *);
 void	xfs_buf_iodone(struct xfs_buf *, struct xfs_log_item *);
 bool	xfs_buf_resubmit_failed_buffers(struct xfs_buf *,
 					struct list_head *);
+bool	xfs_buf_log_check_iovec(struct xfs_log_iovec *iovec);
 
 extern kmem_zone_t	*xfs_buf_item_zone;
 

fs/xfs/xfs_dquot.c

@@ -137,7 +137,7 @@ xfs_qm_adjust_dqtimers(
 		    (d->d_blk_hardlimit &&
 		     (be64_to_cpu(d->d_bcount) >
 		      be64_to_cpu(d->d_blk_hardlimit)))) {
-			d->d_btimer = cpu_to_be32(get_seconds() +
+			d->d_btimer = cpu_to_be32(ktime_get_real_seconds() +
 					mp->m_quotainfo->qi_btimelimit);
 		} else {
 			d->d_bwarns = 0;
@@ -160,7 +160,7 @@ xfs_qm_adjust_dqtimers(
 		    (d->d_ino_hardlimit &&
 		     (be64_to_cpu(d->d_icount) >
 		      be64_to_cpu(d->d_ino_hardlimit)))) {
-			d->d_itimer = cpu_to_be32(get_seconds() +
+			d->d_itimer = cpu_to_be32(ktime_get_real_seconds() +
 					mp->m_quotainfo->qi_itimelimit);
 		} else {
 			d->d_iwarns = 0;
@@ -183,7 +183,7 @@ xfs_qm_adjust_dqtimers(
 		    (d->d_rtb_hardlimit &&
 		     (be64_to_cpu(d->d_rtbcount) >
 		      be64_to_cpu(d->d_rtb_hardlimit)))) {
-			d->d_rtbtimer = cpu_to_be32(get_seconds() +
+			d->d_rtbtimer = cpu_to_be32(ktime_get_real_seconds() +
 					mp->m_quotainfo->qi_rtbtimelimit);
 		} else {
 			d->d_rtbwarns = 0;

fs/xfs/xfs_file.c

@@ -187,7 +187,12 @@ xfs_file_dio_aio_read(
 
 	file_accessed(iocb->ki_filp);
 
-	xfs_ilock(ip, XFS_IOLOCK_SHARED);
+	if (iocb->ki_flags & IOCB_NOWAIT) {
+		if (!xfs_ilock_nowait(ip, XFS_IOLOCK_SHARED))
+			return -EAGAIN;
+	} else {
+		xfs_ilock(ip, XFS_IOLOCK_SHARED);
+	}
 	ret = iomap_dio_rw(iocb, to, &xfs_read_iomap_ops, NULL,
 			is_sync_kiocb(iocb));
 	xfs_iunlock(ip, XFS_IOLOCK_SHARED);

fs/xfs/xfs_inode.c

@@ -1518,10 +1518,8 @@ xfs_itruncate_extents_flags(
 	struct xfs_mount	*mp = ip->i_mount;
 	struct xfs_trans	*tp = *tpp;
 	xfs_fileoff_t		first_unmap_block;
-	xfs_fileoff_t		last_block;
 	xfs_filblks_t		unmap_len;
 	int			error = 0;
-	int			done = 0;
 
 	ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL));
 	ASSERT(!atomic_read(&VFS_I(ip)->i_count) ||
@@ -1541,21 +1539,22 @@ xfs_itruncate_extents_flags(
 	 * the end of the file (in a crash where the space is allocated
 	 * but the inode size is not yet updated), simply remove any
 	 * blocks which show up between the new EOF and the maximum
-	 * possible file size.  If the first block to be removed is
-	 * beyond the maximum file size (ie it is the same as last_block),
-	 * then there is nothing to do.
+	 * possible file size.
+	 *
+	 * We have to free all the blocks to the bmbt maximum offset, even if
+	 * the page cache can't scale that far.
 	 */
 	first_unmap_block = XFS_B_TO_FSB(mp, (xfs_ufsize_t)new_size);
-	last_block = XFS_B_TO_FSB(mp, mp->m_super->s_maxbytes);
-	if (first_unmap_block == last_block)
+	if (first_unmap_block >= XFS_MAX_FILEOFF) {
+		WARN_ON_ONCE(first_unmap_block > XFS_MAX_FILEOFF);
 		return 0;
+	}
 
-	ASSERT(first_unmap_block < last_block);
-	unmap_len = last_block - first_unmap_block + 1;
-	while (!done) {
+	unmap_len = XFS_MAX_FILEOFF - first_unmap_block + 1;
+	while (unmap_len > 0) {
 		ASSERT(tp->t_firstblock == NULLFSBLOCK);
-		error = xfs_bunmapi(tp, ip, first_unmap_block, unmap_len, flags,
-				    XFS_ITRUNC_MAX_EXTENTS, &done);
+		error = __xfs_bunmapi(tp, ip, first_unmap_block, &unmap_len,
+				flags, XFS_ITRUNC_MAX_EXTENTS);
 		if (error)
 			goto out;
 
@@ -1575,7 +1574,7 @@ xfs_itruncate_extents_flags(
 	if (whichfork == XFS_DATA_FORK) {
 		/* Remove all pending CoW reservations. */
 		error = xfs_reflink_cancel_cow_blocks(ip, &tp,
-				first_unmap_block, last_block, true);
+				first_unmap_block, XFS_MAX_FILEOFF, true);
 		if (error)
 			goto out;
 

fs/xfs/xfs_ioctl.c

@@ -357,6 +357,7 @@ xfs_attrmulti_attr_get(
 {
 	unsigned char		*kbuf;
 	int			error = -EFAULT;
+	size_t			namelen;
 
 	if (*len > XFS_XATTR_SIZE_MAX)
 		return -EINVAL;
@@ -364,7 +365,9 @@ xfs_attrmulti_attr_get(
 	if (!kbuf)
 		return -ENOMEM;
 
-	error = xfs_attr_get(XFS_I(inode), name, &kbuf, (int *)len, flags);
+	namelen = strlen(name);
+	error = xfs_attr_get(XFS_I(inode), name, namelen, &kbuf, (int *)len,
+			     flags);
 	if (error)
 		goto out_kfree;
 
@@ -386,6 +389,7 @@ xfs_attrmulti_attr_set(
 {
 	unsigned char		*kbuf;
 	int			error;
+	size_t			namelen;
 
 	if (IS_IMMUTABLE(inode) || IS_APPEND(inode))
 		return -EPERM;
@@ -396,7 +400,8 @@ xfs_attrmulti_attr_set(
 	if (IS_ERR(kbuf))
 		return PTR_ERR(kbuf);
 
-	error = xfs_attr_set(XFS_I(inode), name, kbuf, len, flags);
+	namelen = strlen(name);
+	error = xfs_attr_set(XFS_I(inode), name, namelen, kbuf, len, flags);
 	if (!error)
 		xfs_forget_acl(inode, name, flags);
 	kfree(kbuf);
@@ -410,10 +415,12 @@ xfs_attrmulti_attr_remove(
 	uint32_t		flags)
 {
 	int			error;
+	size_t			namelen;
 
 	if (IS_IMMUTABLE(inode) || IS_APPEND(inode))
 		return -EPERM;
-	error = xfs_attr_remove(XFS_I(inode), name, flags);
+	namelen = strlen(name);
+	error = xfs_attr_remove(XFS_I(inode), name, namelen, flags);
 	if (!error)
 		xfs_forget_acl(inode, name, flags);
 	return error;
@@ -462,6 +469,13 @@ xfs_attrmulti_by_handle(
 
 	error = 0;
 	for (i = 0; i < am_hreq.opcount; i++) {
+		if ((ops[i].am_flags & ATTR_ROOT) &&
+		    (ops[i].am_flags & ATTR_SECURE)) {
+			ops[i].am_error = -EINVAL;
+			continue;
+		}
+		ops[i].am_flags &= ~ATTR_KERNEL_FLAGS;
+
 		ops[i].am_error = strncpy_from_user((char *)attr_name,
 				ops[i].am_attrname, MAXNAMELEN);
 		if (ops[i].am_error == 0 || ops[i].am_error == MAXNAMELEN)

fs/xfs/xfs_ioctl32.c

@@ -107,7 +107,7 @@ xfs_ioctl32_bstime_copyin(
 	xfs_bstime_t		*bstime,
 	compat_xfs_bstime_t	__user *bstime32)
 {
-	compat_time_t		sec32;	/* tv_sec differs on 64 vs. 32 */
+	old_time32_t		sec32;	/* tv_sec differs on 64 vs. 32 */
 
 	if (get_user(sec32,		&bstime32->tv_sec)	||
 	    get_user(bstime->tv_nsec,	&bstime32->tv_nsec))
@@ -450,6 +450,13 @@ xfs_compat_attrmulti_by_handle(
 
 	error = 0;
 	for (i = 0; i < am_hreq.opcount; i++) {
+		if ((ops[i].am_flags & ATTR_ROOT) &&
+		    (ops[i].am_flags & ATTR_SECURE)) {
+			ops[i].am_error = -EINVAL;
+			continue;
+		}
+		ops[i].am_flags &= ~ATTR_KERNEL_FLAGS;
+
 		ops[i].am_error = strncpy_from_user((char *)attr_name,
 				compat_ptr(ops[i].am_attrname),
 				MAXNAMELEN);

fs/xfs/xfs_ioctl32.h

@@ -32,7 +32,7 @@
 #endif
 
 typedef struct compat_xfs_bstime {
-	compat_time_t	tv_sec;		/* seconds		*/
+	old_time32_t	tv_sec;		/* seconds		*/
 	__s32		tv_nsec;	/* and nanoseconds	*/
 } compat_xfs_bstime_t;
 

fs/xfs/xfs_iomap.c

@@ -923,7 +923,7 @@ xfs_buffered_write_iomap_begin(
 		xfs_trim_extent(&imap, offset_fsb, end_fsb - offset_fsb);
 
 		/* Trim the mapping to the nearest shared extent boundary. */
-		error = xfs_inode_need_cow(ip, &imap, &shared);
+		error = xfs_bmap_trim_cow(ip, &imap, &shared);
 		if (error)
 			goto out_unlock;
 

fs/xfs/xfs_iops.c

@@ -50,8 +50,10 @@ xfs_initxattrs(
 	int			error = 0;
 
 	for (xattr = xattr_array; xattr->name != NULL; xattr++) {
-		error = xfs_attr_set(ip, xattr->name, xattr->value,
-				      xattr->value_len, ATTR_SECURE);
+		error = xfs_attr_set(ip, xattr->name,
+				     strlen(xattr->name),
+				     xattr->value, xattr->value_len,
+				     ATTR_SECURE);
 		if (error < 0)
 			break;
 	}

fs/xfs/xfs_log_recover.c

@@ -1934,6 +1934,12 @@ xlog_recover_buffer_pass1(
 	struct list_head	*bucket;
 	struct xfs_buf_cancel	*bcp;
 
+	if (!xfs_buf_log_check_iovec(&item->ri_buf[0])) {
+		xfs_err(log->l_mp, "bad buffer log item size (%d)",
+				item->ri_buf[0].i_len);
+		return -EFSCORRUPTED;
+	}
+
 	/*
 	 * If this isn't a cancel buffer item, then just return.
 	 */

fs/xfs/xfs_ondisk.h

@@ -111,6 +111,7 @@ xfs_check_ondisk_structs(void)
 	XFS_CHECK_STRUCT_SIZE(xfs_dir2_sf_hdr_t,		10);
 
 	/* log structures */
+	XFS_CHECK_STRUCT_SIZE(struct xfs_buf_log_format,	88);
 	XFS_CHECK_STRUCT_SIZE(struct xfs_dq_logformat,		24);
 	XFS_CHECK_STRUCT_SIZE(struct xfs_efd_log_format_32,	28);
 	XFS_CHECK_STRUCT_SIZE(struct xfs_efd_log_format_64,	32);

fs/xfs/xfs_qm.h

@@ -64,9 +64,9 @@ struct xfs_quotainfo {
 	struct xfs_inode	*qi_pquotaip;	/* project quota inode */
 	struct list_lru	 qi_lru;
 	int		 qi_dquots;
-	time_t		 qi_btimelimit;	 /* limit for blks timer */
-	time_t		 qi_itimelimit;	 /* limit for inodes timer */
-	time_t		 qi_rtbtimelimit;/* limit for rt blks timer */
+	time64_t	 qi_btimelimit;	 /* limit for blks timer */
+	time64_t	 qi_itimelimit;	 /* limit for inodes timer */
+	time64_t	 qi_rtbtimelimit;/* limit for rt blks timer */
 	xfs_qwarncnt_t	 qi_bwarnlimit;	 /* limit for blks warnings */
 	xfs_qwarncnt_t	 qi_iwarnlimit;	 /* limit for inodes warnings */
 	xfs_qwarncnt_t	 qi_rtbwarnlimit;/* limit for rt blks warnings */

fs/xfs/xfs_quotaops.c

@@ -37,9 +37,9 @@ xfs_qm_fill_state(
 	tstate->flags |= QCI_SYSFILE;
 	tstate->blocks = ip->i_d.di_nblocks;
 	tstate->nextents = ip->i_d.di_nextents;
-	tstate->spc_timelimit = q->qi_btimelimit;
-	tstate->ino_timelimit = q->qi_itimelimit;
-	tstate->rt_spc_timelimit = q->qi_rtbtimelimit;
+	tstate->spc_timelimit = (u32)q->qi_btimelimit;
+	tstate->ino_timelimit = (u32)q->qi_itimelimit;
+	tstate->rt_spc_timelimit = (u32)q->qi_rtbtimelimit;
 	tstate->spc_warnlimit = q->qi_bwarnlimit;
 	tstate->ino_warnlimit = q->qi_iwarnlimit;
 	tstate->rt_spc_warnlimit = q->qi_rtbwarnlimit;

fs/xfs/xfs_reflink.c

@@ -223,8 +223,8 @@ xfs_reflink_trim_around_shared(
 	}
 }
 
-bool
-xfs_inode_need_cow(
+int
+xfs_bmap_trim_cow(
 	struct xfs_inode	*ip,
 	struct xfs_bmbt_irec	*imap,
 	bool			*shared)
@@ -327,7 +327,7 @@ xfs_find_trim_cow_extent(
 	if (cmap->br_startoff > offset_fsb) {
 		xfs_trim_extent(imap, imap->br_startoff,
 				cmap->br_startoff - imap->br_startoff);
-		return xfs_inode_need_cow(ip, imap, shared);
+		return xfs_bmap_trim_cow(ip, imap, shared);
 	}
 
 	*shared = true;
@@ -1457,7 +1457,8 @@ xfs_reflink_clear_inode_flag(
 	 * We didn't find any shared blocks so turn off the reflink flag.
 	 * First, get rid of any leftover CoW mappings.
 	 */
-	error = xfs_reflink_cancel_cow_blocks(ip, tpp, 0, NULLFILEOFF, true);
+	error = xfs_reflink_cancel_cow_blocks(ip, tpp, 0, XFS_MAX_FILEOFF,
+			true);
 	if (error)
 		return error;
 

fs/xfs/xfs_reflink.h

@@ -22,7 +22,7 @@ extern int xfs_reflink_find_shared(struct xfs_mount *mp, struct xfs_trans *tp,
 		xfs_agblock_t *fbno, xfs_extlen_t *flen, bool find_maximal);
 extern int xfs_reflink_trim_around_shared(struct xfs_inode *ip,
 		struct xfs_bmbt_irec *irec, bool *shared);
-bool xfs_inode_need_cow(struct xfs_inode *ip, struct xfs_bmbt_irec *imap,
+int xfs_bmap_trim_cow(struct xfs_inode *ip, struct xfs_bmbt_irec *imap,
 		bool *shared);
 
 int xfs_reflink_allocate_cow(struct xfs_inode *ip, struct xfs_bmbt_irec *imap,

fs/xfs/xfs_super.c

@@ -193,32 +193,6 @@ xfs_fs_show_options(
 	return 0;
 }
 
-static uint64_t
-xfs_max_file_offset(
-	unsigned int		blockshift)
-{
-	unsigned int		pagefactor = 1;
-	unsigned int		bitshift = BITS_PER_LONG - 1;
-
-	/* Figure out maximum filesize, on Linux this can depend on
-	 * the filesystem blocksize (on 32 bit platforms).
-	 * __block_write_begin does this in an [unsigned] long long...
-	 *      page->index << (PAGE_SHIFT - bbits)
-	 * So, for page sized blocks (4K on 32 bit platforms),
-	 * this wraps at around 8Tb (hence MAX_LFS_FILESIZE which is
-	 *      (((u64)PAGE_SIZE << (BITS_PER_LONG-1))-1)
-	 * but for smaller blocksizes it is less (bbits = log2 bsize).
-	 */
-
-#if BITS_PER_LONG == 32
-	ASSERT(sizeof(sector_t) == 8);
-	pagefactor = PAGE_SIZE;
-	bitshift = BITS_PER_LONG;
-#endif
-
-	return (((uint64_t)pagefactor) << bitshift) - 1;
-}
-
 /*
  * Set parameters for inode allocation heuristics, taking into account
  * filesystem size and inode32/inode64 mount options; i.e. specifically
@@ -1424,6 +1398,26 @@ xfs_fc_fill_super(
 	if (error)
 		goto out_free_sb;
 
+	/*
+	 * XFS block mappings use 54 bits to store the logical block offset.
+	 * This should suffice to handle the maximum file size that the VFS
+	 * supports (currently 2^63 bytes on 64-bit and ULONG_MAX << PAGE_SHIFT
+	 * bytes on 32-bit), but as XFS and VFS have gotten the s_maxbytes
+	 * calculation wrong on 32-bit kernels in the past, we'll add a WARN_ON
+	 * to check this assertion.
+	 *
+	 * Avoid integer overflow by comparing the maximum bmbt offset to the
+	 * maximum pagecache offset in units of fs blocks.
+	 */
+	if (XFS_B_TO_FSBT(mp, MAX_LFS_FILESIZE) > XFS_MAX_FILEOFF) {
+		xfs_warn(mp,
+"MAX_LFS_FILESIZE block offset (%llu) exceeds extent map maximum (%llu)!",
+			 XFS_B_TO_FSBT(mp, MAX_LFS_FILESIZE),
+			 XFS_MAX_FILEOFF);
+		error = -EINVAL;
+		goto out_free_sb;
+	}
+
 	error = xfs_filestream_mount(mp);
 	if (error)
 		goto out_free_sb;
@@ -1435,7 +1429,7 @@ xfs_fc_fill_super(
 	sb->s_magic = XFS_SUPER_MAGIC;
 	sb->s_blocksize = mp->m_sb.sb_blocksize;
 	sb->s_blocksize_bits = ffs(sb->s_blocksize) - 1;
-	sb->s_maxbytes = xfs_max_file_offset(sb->s_blocksize_bits);
+	sb->s_maxbytes = MAX_LFS_FILESIZE;
 	sb->s_max_links = XFS_MAXLINK;
 	sb->s_time_gran = 1;
 	sb->s_time_min = S32_MIN;

fs/xfs/xfs_trans_dquot.c

@@ -580,7 +580,7 @@ xfs_trans_dqresv(
 {
 	xfs_qcnt_t		hardlimit;
 	xfs_qcnt_t		softlimit;
-	time_t			timer;
+	time64_t		timer;
 	xfs_qwarncnt_t		warns;
 	xfs_qwarncnt_t		warnlimit;
 	xfs_qcnt_t		total_count;
@@ -635,7 +635,8 @@ xfs_trans_dqresv(
 				goto error_return;
 			}
 			if (softlimit && total_count > softlimit) {
-				if ((timer != 0 && get_seconds() > timer) ||
+				if ((timer != 0 &&
+				     ktime_get_real_seconds() > timer) ||
 				    (warns != 0 && warns >= warnlimit)) {
 					xfs_quota_warn(mp, dqp,
 						       QUOTA_NL_BSOFTLONGWARN);
@@ -662,7 +663,8 @@ xfs_trans_dqresv(
 				goto error_return;
 			}
 			if (softlimit && total_count > softlimit) {
-				if  ((timer != 0 && get_seconds() > timer) ||
+				if  ((timer != 0 &&
+				      ktime_get_real_seconds() > timer) ||
 				     (warns != 0 && warns >= warnlimit)) {
 					xfs_quota_warn(mp, dqp,
 						       QUOTA_NL_ISOFTLONGWARN);

fs/xfs/xfs_xattr.c

@@ -24,6 +24,7 @@ xfs_xattr_get(const struct xattr_handler *handler, struct dentry *unused,
 	int xflags = handler->flags;
 	struct xfs_inode *ip = XFS_I(inode);
 	int error, asize = size;
+	size_t namelen = strlen(name);
 
 	/* Convert Linux syscall to XFS internal ATTR flags */
 	if (!size) {
@@ -31,7 +32,8 @@ xfs_xattr_get(const struct xattr_handler *handler, struct dentry *unused,
 		value = NULL;
 	}
 
-	error = xfs_attr_get(ip, name, (unsigned char **)&value, &asize, xflags);
+	error = xfs_attr_get(ip, name, namelen, (unsigned char **)&value,
+			     &asize, xflags);
 	if (error)
 		return error;
 	return asize;
@@ -67,6 +69,7 @@ xfs_xattr_set(const struct xattr_handler *handler, struct dentry *unused,
 	int			xflags = handler->flags;
 	struct xfs_inode	*ip = XFS_I(inode);
 	int			error;
+	size_t			namelen = strlen(name);
 
 	/* Convert Linux syscall to XFS internal ATTR flags */
 	if (flags & XATTR_CREATE)
@@ -74,10 +77,11 @@ xfs_xattr_set(const struct xattr_handler *handler, struct dentry *unused,
 	if (flags & XATTR_REPLACE)
 		xflags |= ATTR_REPLACE;
 
-	if (!value)
-		return xfs_attr_remove(ip, (unsigned char *)name, xflags);
-	error = xfs_attr_set(ip, (unsigned char *)name,
-				(void *)value, size, xflags);
+	if (value)
+		error = xfs_attr_set(ip, name, namelen, (void *)value, size,
+				xflags);
+	else
+		error = xfs_attr_remove(ip, name, namelen, xflags);
 	if (!error)
 		xfs_forget_acl(inode, name, xflags);